Adaptive on-line similarity measure for direct visual tracking

作者：

Highlights：

• We present an adaptive metric for measuring the similarity of a target for the purpose of visual tracking.

• This metric assigns a robust weight to each matching error based on the error type.

• A histogram-based classifier is learned on-line to determine the error type.

• The proposed robust metric dynamically adapts to the actual appearance changes by tuning its parameters.

摘要

•We present an adaptive metric for measuring the similarity of a target for the purpose of visual tracking.•This metric assigns a robust weight to each matching error based on the error type.•A histogram-based classifier is learned on-line to determine the error type.•The proposed robust metric dynamically adapts to the actual appearance changes by tuning its parameters.

论文关键词：Adaptive metric,Similarity measure,Visual tracking,Template matching

论文评审过程：Received 18 April 2013, Revised 11 November 2013, Accepted 30 January 2014, Available online 8 February 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.01.007